我开始学习使用 SQL Server 进行数据挖掘，我很好奇 SQL Server Integration Services 是否能够从英文文本中执行术语提取。然而，我有兴趣从非英语文本（基本上是乌克兰语）执行文本挖掘。所以这些就是问题：
- 有没有办法在 SSIS 中实现非英语文本的术语提取？如果是，那么任何合适的资源将不胜感激：）
- 如果第一个问题的答案是肯定的，我想知道是否已经有一些针对非英语文本的自定义解决方案。
提前致谢：）
I started learning Data Mining with SQL Server and I was curious that SQL Server Integration Services is capable to perform Term Extraction from English text. However I'm interested to perform Text Mining from non-English text, basically from Ukrainian. So these are the very questions:
- Is there a way to implement Term Extraction from non-English text in SSIS? If yes then any suitable resources would be appreciated:)
- If the answer for the first question is positive I would like to know if there are already some custom solutions for non-English text.
Thanks in advance:)
发布评论
评论（1）
文档声明术语提取转换仅支持英语，并且没有提到添加其他语言的机制。
因此，我假设您需要找到某种可以使用乌克兰语文本进行术语提取的工具，并找出如何将其集成到 SSIS 中。找到这样的工具并不是真正的 SSIS 问题，而是一般的 NLP 或语言学问题，所以你可能会在另一个论坛得到更好的答案。
The documentation states that the term extraction transformation supports only English, and there's no mention of a mechanism for adding other languages.
Therefore, I would assume that you need to find some sort of tool that can do term extraction with Ukrainian text, and work out how to integrate it into SSIS. Finding a tool like that isn't really an SSIS issue, it's a general NLP or linguistics question, so you might get a better answer in another forum.